From a3d8197930b9e2c07862186d23ee192dc0347ff4 Mon Sep 17 00:00:00 2001 From: Robert Sachunsky Date: Tue, 30 Sep 2025 21:50:21 +0200 Subject: [PATCH] makefile: update model URL --- Makefile | 50 ++++++++++++++++++++++++++++---------------------- 1 file changed, 28 insertions(+), 22 deletions(-) diff --git a/Makefile b/Makefile index dd95c0a..357aa47 100644 --- a/Makefile +++ b/Makefile @@ -13,10 +13,16 @@ DOCKER ?= docker #SEG_MODEL := https://github.com/qurator-spk/eynollah/releases/download/v0.3.0/models_eynollah.tar.gz #SEG_MODEL := https://github.com/qurator-spk/eynollah/releases/download/v0.3.1/models_eynollah.tar.gz SEG_MODEL := https://zenodo.org/records/17194824/files/models_layout_v0_5_0.tar.gz?download=1 +SEG_MODELFILE = $(notdir $(patsubst %?download=1,%,$(SEG_MODEL))) +SEG_MODELNAME = $(SEG_MODELFILE:%.tar.gz=%) BIN_MODEL := https://github.com/qurator-spk/sbb_binarization/releases/download/v0.0.11/saved_model_2021_03_09.zip +BIN_MODELFILE = $(notdir $(BIN_MODEL)) +BIN_MODELNAME := default-2021-03-09 -OCR_MODEL := https://zenodo.org/records/17194824/files/models_ocr_v0_5_0.tar.gz?download=1 +OCR_MODEL := https://zenodo.org/records/17236998/files/models_ocr_v0_5_1.tar.gz?download=1 +OCR_MODELFILE = $(notdir $(patsubst %?download=1,%,$(OCR_MODEL))) +OCR_MODELNAME = $(OCR_MODELFILE:%.tar.gz=%) PYTEST_ARGS ?= -vv --isolate @@ -31,7 +37,8 @@ help: @echo " install Install package with pip" @echo " install-dev Install editable with pip" @echo " deps-test Install test dependencies with pip" - @echo " models Download and extract models to $(CURDIR)/models_layout_v0_5_0" + @echo " models Download and extract models to $(CURDIR):" + @echo " $(BIN_MODELNAME) $(SEG_MODELNAME) $(OCR_MODELNAME)" @echo " smoke-test Run simple CLI check" @echo " ocrd-test Run OCR-D CLI check" @echo " test Run unit tests" @@ -42,33 +49,29 @@ help: @echo " PYTEST_ARGS pytest args for 'test' (Set to '-s' to see log output during test execution, '-vv' to see individual tests. [$(PYTEST_ARGS)]" @echo " SEG_MODEL URL of 'models' archive to download for segmentation 'test' [$(SEG_MODEL)]" @echo " BIN_MODEL URL of 'models' archive to download for binarization 'test' [$(BIN_MODEL)]" + @echo " OCR_MODEL URL of 'models' archive to download for binarization 'test' [$(OCR_MODEL)]" @echo "" # END-EVAL # Download and extract models to $(PWD)/models_layout_v0_5_0 -models: models_layout_v0_5_0 models_ocr_v0_5_0 default-2021-03-09 +models: $(BIN_MODELNAME) $(SEG_MODELNAME) $(OCR_MODELNAME) -models_layout_v0_5_0: models_layout_v0_5_0.tar.gz - tar zxf models_layout_v0_5_0.tar.gz - -models_layout_v0_5_0.tar.gz: +$(BIN_MODELFILE): + wget -O $@ $(BIN_MODEL) +$(SEG_MODELFILE): wget -O $@ $(SEG_MODEL) - -models_ocr_v0_5_0: models_ocr_v0_5_0.tar.gz - tar zxf models_ocr_v0_5_0.tar.gz - -models_ocr_v0_5_0.tar.gz: +$(OCR_MODELFILE): wget -O $@ $(OCR_MODEL) -default-2021-03-09: $(notdir $(BIN_MODEL)) - unzip $(notdir $(BIN_MODEL)) +$(BIN_MODELNAME): $(BIN_MODELFILE) mkdir $@ - mv $(basename $(notdir $(BIN_MODEL))) $@ - -$(notdir $(BIN_MODEL)): - wget $(BIN_MODEL) + unzip -d $@ $< +$(SEG_MODELNAME): $(SEG_MODELFILE) + tar zxf $< +$(OCR_MODELNAME): $(OCR_MODELFILE) + tar zxf $< build: $(PIP) install build @@ -82,7 +85,10 @@ install: install-dev: $(PIP) install -e .$(and $(EXTRAS),[$(EXTRAS)]) -deps-test: models_layout_v0_5_0 +ifeq (OCR,$(findstring OCR, $(EXTRAS))) +deps-test: $(OCR_MODELNAME) +endif +deps-test: $(BIN_MODELNAME) $(SEG_MODELNAME) $(PIP) install -r requirements-test.txt smoke-test: TMPDIR != mktemp -d @@ -123,9 +129,9 @@ ocrd-test: tests/resources/kant_aufklaerung_1784_0020.tif $(RM) -r $(TMPDIR) # Run unit tests -test: export MODELS_LAYOUT=$(CURDIR)/models_layout_v0_5_0 -test: export MODELS_OCR=$(CURDIR)/models_ocr_v0_5_0 -test: export MODELS_BIN=$(CURDIR)/default-2021-03-09 +test: export MODELS_LAYOUT=$(CURDIR)/$(SEG_MODELNAME) +test: export MODELS_OCR=$(CURDIR)/$(OCR_MODELNAME) +test: export MODELS_BIN=$(CURDIR)/$(BIN_MODELNAME) test: $(PYTHON) -m pytest tests --durations=0 --continue-on-collection-errors $(PYTEST_ARGS)